{"id":"https://openalex.org/W3129910207","doi":"https://doi.org/10.1186/s13636-021-00203-w","title":"Dynamically localizing multiple speakers based on the time-frequency domain","display_name":"Dynamically localizing multiple speakers based on the time-frequency domain","publication_year":2021,"publication_date":"2021-04-08","ids":{"openalex":"https://openalex.org/W3129910207","doi":"https://doi.org/10.1186/s13636-021-00203-w","mag":"3129910207"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00203-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00203-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00203-w","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00203-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057955788","display_name":"Hodaya Hammer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Hodaya Hammer","raw_affiliation_strings":["Faculty of Electrical Engineering, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["Faculty of Electrical Engineering, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Faculty of Electrical Engineering, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Electrical Engineering, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical Engineering, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057955788"],"corresponding_institution_ids":["https://openalex.org/I4210160816"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.3949,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9310714,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7542769312858582},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.6754339337348938},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.6271576881408691},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5948847532272339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5432658195495605},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5388152003288269},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5083085894584656},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5061871409416199},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5034586787223816},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.48796147108078003},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4777871072292328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46215561032295227},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.448047012090683},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.4415387213230133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4274480938911438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11499965190887451},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1053301990032196},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10298401117324829},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.09657379984855652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542769312858582},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.6754339337348938},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.6271576881408691},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5948847532272339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5432658195495605},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5388152003288269},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5083085894584656},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5061871409416199},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5034586787223816},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.48796147108078003},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4777871072292328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46215561032295227},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.448047012090683},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.4415387213230133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4274480938911438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11499965190887451},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1053301990032196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10298401117324829},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.09657379984855652},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-021-00203-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00203-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00203-w","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:65f5263b056245d0901e2e1a6c0a5ad7","is_oa":true,"landing_page_url":"https://doaj.org/article/65f5263b056245d0901e2e1a6c0a5ad7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-10 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00203-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00203-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00203-w","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4864788181","display_name":null,"funder_award_id":"3-16416","funder_id":"https://openalex.org/F4320323706","funder_display_name":"Ministry of Science and Technology, Israel"},{"id":"https://openalex.org/G5399556803","display_name":null,"funder_award_id":"This project has received funding from the Europea","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7556389956","display_name":null,"funder_award_id":"871245","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G776759023","display_name":null,"funder_award_id":"Horizon 2020 Research and Innovation Programme und","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8258793481","display_name":null,"funder_award_id":"871245","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323706","display_name":"Ministry of Science and Technology, Israel","ror":"https://ror.org/02heb2n75"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3129910207.pdf","grobid_xml":"https://content.openalex.org/works/W3129910207.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1603075283","https://openalex.org/W1772191655","https://openalex.org/W1901129140","https://openalex.org/W1987906574","https://openalex.org/W1996304098","https://openalex.org/W2039760476","https://openalex.org/W2053112522","https://openalex.org/W2090024980","https://openalex.org/W2095946761","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2117678320","https://openalex.org/W2128977628","https://openalex.org/W2147665979","https://openalex.org/W2155638623","https://openalex.org/W2551990143","https://openalex.org/W2568308529","https://openalex.org/W2586642235","https://openalex.org/W2611943505","https://openalex.org/W2784289299","https://openalex.org/W2790154031","https://openalex.org/W2884822476","https://openalex.org/W2885219692","https://openalex.org/W2951249128","https://openalex.org/W2962866211","https://openalex.org/W2963881378","https://openalex.org/W2963941778","https://openalex.org/W2971656978","https://openalex.org/W2987372735","https://openalex.org/W2998678989","https://openalex.org/W3003337611","https://openalex.org/W3011281702","https://openalex.org/W3021261768","https://openalex.org/W3096915137","https://openalex.org/W3100871498","https://openalex.org/W3102937397","https://openalex.org/W6600020239","https://openalex.org/W6600195515","https://openalex.org/W6629264894","https://openalex.org/W6632699545","https://openalex.org/W6636602988","https://openalex.org/W6701294789","https://openalex.org/W6817289261","https://openalex.org/W6834057695"],"related_works":["https://openalex.org/W2767651786","https://openalex.org/W2912288872","https://openalex.org/W564581980","https://openalex.org/W2161947961","https://openalex.org/W1947057263","https://openalex.org/W2355274186","https://openalex.org/W2116623987","https://openalex.org/W2141743132","https://openalex.org/W2141785977","https://openalex.org/W3129910207"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"study,":[3],"we":[4,113],"present":[5],"a":[6,16,34,40,111],"deep":[7],"neural":[8],"network-based":[9],"online":[10],"multi-speaker":[11],"localization":[12],"algorithm":[13,100],"based":[14],"on":[15],"multi-microphone":[17],"array.":[18],"Following":[19],"the":[20,25,58,68,98,117,128,131],"W-disjoint":[21],"orthogonality":[22],"principle":[23],"in":[24,91],"spectral":[26],"domain,":[27],"time-frequency":[28],"(TF)":[29],"bin":[30],"is":[31,50,120],"dominated":[32],"by":[33,39,127],"single":[35,41],"speaker":[36],"and":[37,72,75,81,88,93,105],"hence":[38],"direction":[42],"of":[43,123,130],"arrival":[44],"(DOA).":[45],"A":[46],"fully":[47],"convolutional":[48],"network":[49,69],"trained":[51],"with":[52],"instantaneous":[53],"spatial":[54],"features":[55],"to":[56,70],"estimate":[57],"DOA":[59],"for":[60],"each":[61],"TF":[62,133],"bin.":[63],"The":[64],"high-resolution":[65],"classification":[66],"enables":[67],"accurately":[71],"simultaneously":[73],"localize":[74],"track":[76],"multiple":[77],"speakers,":[78],"both":[79,103],"static":[80,92],"dynamic.":[82],"Elaborated":[83],"experimental":[84],"study":[85],"using":[86],"simulated":[87],"real-life":[89],"recordings":[90],"dynamic":[94],"scenarios":[95],"demonstrates":[96],"that":[97,116],"proposed":[99,118],"significantly":[101],"outperforms":[102],"classic":[104],"recent":[106],"deep-learning-based":[107],"algorithms.":[108],"Finally,":[109],"as":[110],"byproduct,":[112],"further":[114],"show":[115],"method":[119],"also":[121],"capable":[122],"separating":[124],"moving":[125],"speakers":[126],"application":[129],"obtained":[132],"masks.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
